Structural analysis method and information processing apparatus

Abstract

An information processing apparatus generates a feature vector for each of a plurality of nodes included in an element in mesh data, based on a location of the corresponding node, an elastic modulus at the corresponding node, and stress applied to the corresponding node. The information processing apparatus enters the feature vectors of the nodes to a trained machine learning model, performs a convolutional operation on the feature vectors of the nodes, and estimates an element stiffness matrix indicating stiffness of the element based on a result of the convolutional operation.

What is claimed is: 
     
         1 . A non-transitory computer-readable recording medium storing therein a computer program that causes a computer to execute a process comprising:
 generating a feature vector for each node of a plurality of nodes included in an element in mesh data, based on a location of the each node, an elastic modulus at the each node, and stress applied to the each node;   entering feature vectors of the plurality of nodes to a trained machine learning model;   performing a convolutional operation on the feature vectors of the plurality of nodes; and   estimating an element stiffness matrix indicating stiffness of the element based on a result of the convolutional operation.   
     
     
         2 . The non-transitory computer-readable recording medium according to  claim 1 , wherein the machine learning model is a graph convolutional neural network. 
     
     
         3 . The non-transitory computer-readable recording medium according to  claim 1 , wherein the estimating includes estimating a plurality of element stiffness matrixes corresponding to a plurality of elements in parallel by using a graphics processing unit (GPU). 
     
     
         4 . The non-transitory computer-readable recording medium according to  claim 1 ,
 wherein the process further includes generating an adjacency matrix indicating that each of the plurality of nodes in the element is adjacent to all other nodes, and   wherein the convolutional operation is performed based on the adjacency matrix.   
     
     
         5 . The non-transitory computer-readable recording medium according to  claim 1 , wherein information about the location includes an initial location of the each node and a displacement amount of the each node computed in a previous time step on a simulation. 
     
     
         6 . The non-transitory computer-readable recording medium according to  claim 1 , wherein the generating includes generating the feature vector based on a shape differentiation matrix indicating differentiation of an interpolation function between the each node and another node, in addition to the location, the elastic modulus, and the stress. 
     
     
         7 . The non-transitory computer-readable recording medium according to  claim 1 , wherein the process further includes
 generating another feature vector for each of a plurality of other nodes included in another element, performing a finite element method simulation, generating another element stiffness matrix corresponding to the another element, and training the machine learning model by using training data including the another feature vector and the another element stiffness matrix.   
     
     
         8 . A structural analysis method comprising:
 generating, by a processor, a feature vector for each node of a plurality of nodes included in an element in mesh data, based on a location of the each node, an elastic modulus at the each node, and stress applied to the each node;   entering, by the processor, feature vectors of the plurality of nodes to a trained machine learning model;   performing, by the processor, a convolutional operation on the feature vectors of the plurality of nodes; and   estimating, by the processor, an element stiffness matrix indicating stiffness of the element based on a result of the convolutional operation.   
     
     
         9 . An information processing apparatus comprising:
 a memory configured to store a trained machine learning model; and   a processor coupled to the memory and the processor configured to:   generate a feature vector for each node of a plurality of nodes included in an element in mesh data, based on a location of the each node, an elastic modulus at the each node, and stress applied to the each node;   entering feature vectors of the plurality of nodes to the machine learning model;   performing a convolutional operation on the feature vectors of the plurality of nodes; and   estimating an element stiffness matrix indicating stiffness of the element based on a result of the convolutional operation.